Follow-up visit-based resident health monitoring method, device, equipment and medium

Through intelligent devices, health data and questionnaires are collected, health monitoring models are built, and continuous follow-up and screening are carried out, which solves the existing problems of time-consuming and labor-intensive health monitoring and monitoring of special populations, and achieves efficient and continuous health monitoring and prevention effects.

CN118983087APending Publication Date: 2024-11-19MEDISHARE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410977497.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The existing health monitoring technology is time-consuming and labor-intensive, and the economic cost is high. The gap between the two physical examinations may be too long, resulting in a decrease in the accuracy of health status evaluation, and it is difficult for special groups to monitor, the grassroots work pressure is high, and health information is cumbersome. , inefficient.

Method used

Adopt follow-up-based residents' health monitoring method, collect health data through intelligent devices, combine questionnaires, use credibility analysis and health level models to build residents' health monitoring models, conduct continuous follow-up and screening, and promptly remind high risk of disease. Reduce delays in the disease.

Benefits of technology

It has achieved efficient and continuous follow-up of residents' health monitoring, reduced delays in the disease caused by no physical examination, saved manpower and material resources, improved the detection rate of invisible diseases, reduced the workload at the grassroots level, and timely discovered and prevented diseases.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118983087A_ABST
    Figure CN118983087A_ABST
Patent Text Reader

Abstract

The invention relates to a follow-up visit-based resident health monitoring method, device and equipment and a medium, and belongs to the technical field of health monitoring. The method comprises the following steps: collecting resident health monitoring data and uploading the resident health monitoring data to an intelligent health monitoring database; checking the resident health monitoring data through credibility analysis, and obtaining a resident health monitoring checking result; resident health monitoring coefficients are obtained through the resident health monitoring data, the resident health monitoring coefficients comprise resident information data risk coefficients and resident health data risk coefficients, a resident health monitoring model is constructed through the resident health monitoring coefficients, and resident health levels are obtained; acquiring follow-up visit information based on the health level of the resident, performing follow-up visit on the resident through the follow-up visit information until the resident dies, and acquiring follow-up visit health monitoring data; and screening the follow-up health monitoring data through data screening, and obtaining a follow-up screening result. Long-term monitoring and follow-up visit of resident health conditions are realized, resident disease hidden dangers are eliminated in time, disease delay is prevented, health monitoring of special people is facilitated, basic level work pressure is reduced, and health monitoring work efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of health monitoring, and specifically relates to a resident health monitoring method, device, equipment and medium based on follow-up. Background Art

[0002] At present, with the improvement of public health awareness, health monitoring has received extensive attention. Most residents conduct health monitoring through physical examinations, which is time-consuming, labor-intensive, and economically costly. There is a phenomenon that the blank period between two physical examinations may be too long, resulting in a decrease in the accuracy of the last physical examination results in evaluating the current health status of residents. In addition, most health monitoring relies on the self-consciousness of residents. Residents often conduct health monitoring in specific periods, such as the onset period or sub-health period. When they do not feel unwell, they may not conduct health monitoring, resulting in delayed disease treatment. Special groups, such as the elderly and the disabled, are not convenient to go to the hospital for monitoring and need to rely on the community or volunteers for help, which increases the pressure of grassroots work. In addition, special groups may have difficulty using smart devices and need to conduct health status surveys through paper methods. The entry of paper health information requires a lot of time and energy. Summary of the invention

[0003] In order to solve the above problems existing in the prior art, the present invention provides a resident health monitoring method, device, equipment and medium based on follow-up.

[0004] The purpose of the present invention can be achieved through the following technical solutions:

[0005] A resident health monitoring method based on follow-up, the implementation of which comprises the following steps:

[0006] S1: Collecting resident health monitoring data and uploading it to the intelligent health monitoring database, wherein the resident health monitoring data includes resident information data and resident health data, wherein the resident health data includes resident basic health data, resident in-depth health data, and resident electronic self-assessment health data;

[0007] S2: verifying the resident health monitoring data through credibility analysis and obtaining resident health monitoring verification results, wherein the resident health monitoring verification results include resident health monitoring data credibility results and resident health monitoring data deviation results;

[0008] S3: Obtain a resident health monitoring coefficient through the resident health monitoring data, the resident health monitoring coefficient includes a resident information data risk coefficient and a resident health data risk coefficient, and construct a resident health monitoring model through the resident health monitoring coefficient and obtain the resident health level, the resident health level includes a health level, a sub-health level, a disease precursor level, and a disease level;

[0009] S4: Obtaining follow-up information based on the resident's health level, following up the resident until the resident dies through the follow-up information, and obtaining follow-up health monitoring data;

[0010] S5: Screening the follow-up health monitoring data through data screening and obtaining follow-up screening results, wherein the follow-up screening results include low disease risk results and high disease risk results.

[0011] Preferably, the step S1 specifically includes:

[0012] S101: Acquire the basic health data of the resident through a smart monitoring bracelet, where the basic health data of the resident includes heart rate, respiratory rate, blood oxygen saturation, pressure value, and temperature;

[0013] S102: Acquire the in-depth health data of the resident through health examination, wherein the in-depth health data of the resident includes internal medicine data, surgical data, ENT data, oncology data, and infectious disease data;

[0014] S103: Obtain the residents' self-assessment health questionnaire through a questionnaire survey and extract the residents' electronic self-assessment health data, the questionnaire survey includes an electronic questionnaire survey and a paper questionnaire survey, the residents' self-assessment health questionnaire includes a normal residents' electronic self-assessment health questionnaire and a special residents' paper self-assessment health questionnaire, the residents' electronic self-assessment health data includes normal residents' electronic self-assessment health data and special residents' electronic self-assessment health data, obtain the normal residents' electronic self-assessment health data through the normal residents' electronic self-assessment health questionnaire, process the special residents' paper self-assessment health questionnaire through an improved questionnaire recognition method and obtain the special residents' electronic self-assessment health data.

[0015] Preferably, the step S103 specifically includes:

[0016] S103-1: photographing the paper self-assessment health questionnaire for special residents by means of a photographing device and obtaining a set of images of the paper self-assessment health questionnaire for special residents;

[0017] S103-2: performing normalization processing on the special resident paper self-assessment health questionnaire image set and obtaining a normalized special resident paper self-assessment health questionnaire image set, wherein the normalization processing is to make the size of each special resident paper self-assessment health questionnaire image in the special resident paper self-assessment health questionnaire image set consistent by image cutting;

[0018] S103-3: Based on the weighted average method, the normalized special resident paper self-assessment health questionnaire image set is processed by grayscale and a grayscale special resident paper self-assessment health questionnaire image set is obtained, wherein the grayscale is to convert the color image into a gray image, and the expression of the weighted average method is:

[0019] Gray=0.299R+0.587G+0.114B,

[0020] Among them, Gray is the gray value, R is the brightness of the red channel, G is the brightness of the green channel, and B is the brightness of the blue channel;

[0021] S103-4: Obtain the longest line segment inclination angle of a single image in the grayscale special resident paper self-assessment health questionnaire image set, calculate the inclination angle of the single image according to the longest line segment inclination angle, rotate the single image according to the inclination angle and obtain the modified special resident paper self-assessment health questionnaire image set, the calculation formula of the inclination angle is:

[0022]

[0023] Among them, β is the tilt angle, in degrees, α is the tilt angle of the longest line segment, in degrees;

[0024] S103-5: Identify the modified special resident paper self-assessment health questionnaire image set through character recognition and obtain the special resident electronic self-assessment health data.

[0025] Preferably, the step S2 specifically includes:

[0026] S201: Obtaining the internal consistency credibility coefficient of the resident health monitoring data, the calculation formula of the internal consistency credibility coefficient is:

[0027]

[0028] Among them, γ is the internal consistency reliability coefficient, k is the total number of residents’ health monitoring data, S is the variance of residents’ health monitoring data, S i is the variance of the health monitoring data of the ith resident;

[0029] S202: Preset a credibility threshold, and obtain the resident health monitoring verification result by comparing the internal consistency credibility coefficient with the credibility threshold;

[0030] Determine the resident health monitoring verification result, and when the internal consistency credibility coefficient is greater than or equal to the credibility threshold, feedback the resident health monitoring data credibility result;

[0031] When the internal consistency credibility coefficient is less than the credibility threshold, the deviation result of the resident health monitoring data is fed back to the intelligent health monitoring database and the deviation data is eliminated.

[0032] Preferably, the step S3 specifically includes:

[0033] S301: Obtain a resident information data coefficient through the resident information data, the resident information data coefficient includes a resident family medical history information coefficient, a resident gender information coefficient, a resident age information coefficient, and a resident weight information coefficient, and calculate the resident information data risk coefficient according to the resident information data coefficient. The calculation formula of the resident information data risk coefficient is:

[0034]

[0035] Among them, θ is the risk coefficient of resident information data, v is the coefficient of resident family medical history information, U is the coefficient of resident gender information, O is the coefficient of resident age information, L is the coefficient of resident weight information, and D is the average annual mortality rate of the resident's location, in %;

[0036] S302: Obtain the resident health coefficient through the resident health data, the resident health coefficient includes the resident basic health coefficient, the resident deep health coefficient, and the resident self-assessed health coefficient, and calculate the resident health data risk coefficient according to the resident health coefficient. The calculation formula of the resident health data risk coefficient is:

[0037] η=η1+η2+η3,

[0038] Among them, η is the risk coefficient of residents' health data, η1 is the basic health coefficient of residents, η2 is the deep health coefficient of residents, and η3 is the self-assessed health coefficient of residents;

[0039] S303: Calculate the resident health level evaluation index through the resident health monitoring coefficient and construct a resident health monitoring model. The calculation formula of the resident health level evaluation index is:

[0040]

[0041] Among them, ψ is the resident health level evaluation index, θ is the resident information data risk coefficient, and η is the resident health data risk coefficient;

[0042] S304: Preset a resident health level evaluation threshold, which includes a resident health level threshold, a resident sub-health level threshold, a resident disease precursor level threshold, and a resident disease level threshold, and obtain the resident health level by comparing the resident health level evaluation threshold with the resident health level evaluation index;

[0043] Determine the resident health level evaluation index, and when the resident health level evaluation index is less than or equal to the resident health level threshold, feedback the health level;

[0044] When the resident health level evaluation index is less than or equal to the resident sub-health level threshold and greater than the resident health level threshold, the sub-health level is fed back;

[0045] When the resident health level evaluation index is less than or equal to the resident disease precursor level threshold and greater than the resident sub-health level threshold, the disease precursor level is fed back;

[0046] When the resident health level evaluation index is less than or equal to the resident disease level threshold and greater than the resident disease precursor level threshold, the disease level is fed back.

[0047] Preferably, the step S4 is specifically:

[0048] The follow-up information includes long-term follow-up information, medium-to-long-term follow-up information, medium-to-short-term follow-up information, and short-term follow-up information. Residents of the health level are followed up according to the long-term follow-up information, residents of the sub-health level are followed up according to the medium-to-long-term follow-up information, residents of the disease precursor level are followed up according to the medium-to-short-term follow-up information, and residents of the disease level are followed up according to the short-time span follow-up information. The follow-up health monitoring data includes routine blood data, routine urine data, liver function data, kidney function data, and blood pressure data.

[0049] Preferably, the step S5 is specifically as follows:

[0050] Preset high-risk health thresholds, which include high-risk thresholds for routine blood data, high-risk thresholds for routine urine data, high-risk thresholds for liver function data, high-risk thresholds for renal function data, and high-risk thresholds for blood pressure data, and obtain the follow-up screening results by comparing the follow-up health monitoring data with the high-risk health thresholds;

[0051] Determine the follow-up health monitoring data, and when two or more of the follow-up health monitoring data are greater than the high-risk health threshold, feedback the low-risk result;

[0052] When two or more of the follow-up health monitoring data are greater than the high-risk health threshold, the high risk result is fed back to the resident terminal and a health warning message is sent to the resident.

[0053] A resident health monitoring device based on follow-up, used to execute the above-mentioned resident health monitoring method, comprising a data acquisition module, a data verification module, a health grade evaluation module, a resident follow-up module, and a follow-up screening module;

[0054] The data acquisition module is used to collect resident health monitoring data and upload it to the intelligent health monitoring database. The resident health monitoring data includes resident information data and resident health data. The resident health data includes resident basic health data, resident in-depth health data, and resident electronic self-assessment health data;

[0055] The data verification module is used to verify the resident health monitoring data through credibility analysis and obtain resident health monitoring verification results, wherein the resident health monitoring verification results include resident health monitoring data credibility results and resident health monitoring data deviation results;

[0056] The health grade evaluation module is used to obtain the resident health monitoring coefficient through the resident health monitoring data, and the resident health monitoring coefficient includes the resident information data risk coefficient and the resident health data risk coefficient. The resident health monitoring model is constructed through the resident health monitoring coefficient and the resident health grade is obtained. The resident health grade includes the health grade, sub-health grade, disease precursor grade, and disease grade;

[0057] The resident follow-up module is used to obtain follow-up information based on the resident health level, follow up the resident until the resident dies through the follow-up information, and obtain follow-up health monitoring data;

[0058] The follow-up screening module is used to screen the follow-up health monitoring data through data screening and obtain follow-up screening results, and the follow-up screening results include low disease risk results and high disease risk results.

[0059] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for monitoring resident health when executing the program.

[0060] A storage medium containing computer executable instructions, which are used to execute the above-mentioned resident health monitoring method when executed by a computer processor.

[0061] The beneficial effects of the present invention are:

[0062] (1) Conduct health monitoring by collecting health monitoring data from residents and continuously follow up on people at high risk of disease, thereby reducing the possibility of delayed disease diagnosis due to residents not undergoing physical examinations for various reasons;

[0063] (2) Follow-up visits should be conducted based on the health level of residents. The follow-up time span for healthy people can be appropriately increased, while the follow-up time span for sick people can be shortened, thus saving manpower and material resources in the follow-up process. In addition, measures to shorten the follow-up time span for sick people can help timely detect the onset of illness in the sick people and take timely rescue measures;

[0064] (3) Obtain the disease risk of residents through follow-up health monitoring data, and promptly remind residents when high-risk data appears, so as to prevent residents from getting sick in advance;

[0065] (4) For residents who are unable to fill out electronic questionnaires, paper questionnaires are used, and paper questionnaires are intelligently identified to form electronic data, eliminating the need for manual input, reducing the workload at the grassroots level and improving work efficiency;

[0066] (5) By obtaining in-depth health data of residents, we can comprehensively assess their health status and improve the detection rate of certain hidden diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0068] Figure 1 The present invention is a flowchart of the steps of a resident health monitoring method based on follow-up. DETAILED DESCRIPTION

[0069] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0070] The working principle and use process of the present invention:

[0071] See also Figure 1 , a resident health monitoring method based on follow-up, comprising the following steps:

[0072] S1: Collect resident health monitoring data and upload it to the intelligent health monitoring database. The resident health monitoring data includes resident information data and resident health data. The resident information data includes but is not limited to name, family medical history, gender, age, weight, height, current residence, contact number, ID number, and date of birth. The resident health data includes resident basic health data, resident in-depth health data, and resident electronic self-assessment health data. The expression of the resident health monitoring data is: H = {H1, H2, ..., H n}={R1+T1,R2+T2,…,R n +T n}={R1+X1+Y1+Z1,R2+X2+Y2+Z2,…,R n +X n +Y n +Z n},

[0073] Among them, H is the resident health monitoring data, H1 is the first resident health monitoring data, H2 is the second resident health monitoring data, and H nis the health monitoring data of the nth resident, R1 is the first resident information data, R2 is the second resident information data, R n is the nth resident information data, T1 is the first resident health data, T2 is the second resident health data, T n is the health data of the nth resident, X1 is the basic health data of the first resident, X2 is the basic health data of the second resident, and X n is the basic health data of the nth resident, Y1 is the in-depth health data of the first resident, Y2 is the in-depth health data of the second resident, and Y n is the in-depth health data of the nth resident, Z1 is the electronic self-assessed health data of the first resident, Z2 is the electronic self-assessed health data of the second resident, and Z n is the electronic self-assessed health data of the nth resident, where n is the number of residents;

[0074] S2: verifying the resident health monitoring data through credibility analysis and obtaining resident health monitoring verification results, wherein the resident health monitoring verification results include resident health monitoring data credibility results and resident health monitoring data deviation results;

[0075] S3: Obtain a resident health monitoring coefficient through the resident health monitoring data, the resident health monitoring coefficient includes a resident information data risk coefficient and a resident health data risk coefficient, and construct a resident health monitoring model through the resident health monitoring coefficient and obtain the resident health level, the resident health level includes a health level, a sub-health level, a disease precursor level, and a disease level;

[0076] S4: Obtaining follow-up information based on the resident's health level, following up the resident until the resident dies through the follow-up information, and obtaining follow-up health monitoring data;

[0077] S5: Screening the follow-up health monitoring data through data screening and obtaining follow-up screening results, wherein the follow-up screening results include low disease risk results and high disease risk results.

[0078] In this embodiment, the resident health monitoring data is collected and uploaded to the intelligent health monitoring database, and the resident health monitoring data includes resident information data and resident health data, which can be specifically achieved by the following steps:

[0079] S101: Obtaining basic health data of the resident through a smart monitoring bracelet, wherein the basic health data of the resident is not limited to heart rate, respiratory rate, blood oxygen saturation, pressure value, and temperature;

[0080] S102: Obtain the residents' in-depth health data through health examinations to improve the detection rate of certain invisible diseases. The residents' in-depth health data include but are not limited to internal medicine data, surgical data, ENT data, oncology data, and infectious disease data; the internal medicine data include but are not limited to blood sugar, blood lipids, liver function, and kidney function; the surgical data include but are not limited to external wounds, thyroid function, and lymph nodes; the ENT data include but are not limited to facial deformity, hearing abnormality, breath odor, and nasal bone subsidence and displacement; the oncology data include but are not limited to tumor marker testing, cytological pathology testing, and nuclear magnetic resonance imaging; the infectious disease data include but are not limited to hepatitis B testing, AIDS testing, and syphilis testing;

[0081] S103: Obtain the residents' self-assessment health questionnaire through a questionnaire survey and extract the residents' electronic self-assessment health data, wherein the questionnaire survey includes an electronic questionnaire survey and a paper questionnaire survey, the residents' self-assessment health questionnaire includes a normal residents' electronic self-assessment health questionnaire and a special residents' paper self-assessment health questionnaire, the residents' electronic self-assessment health data includes normal residents' electronic self-assessment health data and special residents' electronic self-assessment health data, the normal residents' electronic self-assessment health data includes but is not limited to dietary patterns, sleep quality, excretion quality, and drinking conditions, the special residents' electronic self-assessment health data includes but is not limited to whether the person is a disabled person, whether the person is a key disease population, dietary patterns, sleep quality, excretion quality, and drinking conditions, the normal residents' electronic self-assessment health data is obtained through the normal residents' electronic self-assessment health questionnaire, the special residents' paper self-assessment health questionnaire is processed by an improved questionnaire recognition method and the special residents' electronic self-assessment health data is obtained, without the need for manual entry, which can reduce the workload at the grassroots level and improve work efficiency.

[0082] In this embodiment, obtaining the residents' self-assessed health questionnaire through a questionnaire survey and extracting the residents' electronic self-assessed health data can be specifically achieved through the following steps:

[0083] S103-1: photographing the paper self-assessment health questionnaire of special residents by a photographing device and obtaining a set of images of the paper self-assessment health questionnaire of special residents, wherein the expression of the set of images of the paper self-assessment health questionnaire of special residents is:

[0084] A={a1,a2,…,a N},

[0085] Among them, A is the image set of the paper self-assessment health questionnaire of special residents, a1 is the image of the paper self-assessment health questionnaire of the first special resident, a2 is the image of the paper self-assessment health questionnaire of the second special resident, and a N This is the image of the paper self-assessment health questionnaire for the Nth special resident;

[0086] S103-2: performing normalization processing on the special resident paper self-assessment health questionnaire image set and obtaining a normalized special resident paper self-assessment health questionnaire image set, wherein the normalization processing is to make the size of each special resident paper self-assessment health questionnaire image in the special resident paper self-assessment health questionnaire image set consistent by image cutting;

[0087] S103-3: Based on the weighted average method, the normalized special resident paper self-assessment health questionnaire image set is processed by grayscale and a grayscale special resident paper self-assessment health questionnaire image set is obtained, wherein the grayscale is to convert the color image into a gray image, and the expression of the weighted average method is:

[0088] Gray=0.299R+0.587G+0.114B,

[0089] Among them, Gray is the gray value, R is the brightness of the red channel, G is the brightness of the green channel, and B is the brightness of the blue channel;

[0090] S103-4: Obtain the longest line segment inclination angle of a single image in the grayscale special resident paper self-assessment health questionnaire image set, calculate the inclination angle of the single image according to the longest line segment inclination angle, rotate the single image according to the inclination angle and obtain the modified special resident paper self-assessment health questionnaire image set, the calculation formula of the inclination angle is:

[0091]

[0092] Among them, β is the tilt angle, in degrees, α is the tilt angle of the longest line segment, in degrees;

[0093] S103-5: Identify the modified special resident paper self-assessment health questionnaire image set by character recognition and obtain the special resident electronic self-assessment health data, wherein the character recognition specifically includes:

[0094] Analyzing the page layout of the modified special resident paper self-assessment health questionnaire image set by a placeholder detection method, wherein the page layout includes text content and other content, and the placeholder detection method is used to distinguish the text content from the other content and extract the text content;

[0095] Analyze the text content by general domain analysis and obtain text block areas, wherein the general domain analysis is used to divide the text content into the text block areas by text intervals;

[0096] Analyze the text block area and obtain similar characters by character contour detection, wherein the character contour detection is used to obtain character features by locating text lines, divide characters according to the character features and obtain the similar characters;

[0097] Obtaining a baseline, extracting the similar characters by cutting the baseline and obtaining a single character;

[0098] The individual characters are identified word by word by an adaptive classifier to obtain the character type, and the character type is compared with a character library to obtain the electronic self-assessment health data of the special resident.

[0099] In this embodiment, the resident health monitoring data is verified through credibility analysis and the resident health monitoring verification results are obtained, and the resident health monitoring verification results include resident health monitoring data credibility results and resident health monitoring data deviation results, which can be specifically implemented through the following steps:

[0100] S201: Obtaining the internal consistency credibility coefficient of the resident health monitoring data, the calculation formula of the internal consistency credibility coefficient is:

[0101]

[0102] Among them, γ is the internal consistency reliability coefficient, k is the total number of residents’ health monitoring data, S is the variance of residents’ health monitoring data, S i is the variance of the health monitoring data of the ith resident;

[0103] S202: Preset a credibility threshold, and obtain the resident health monitoring verification result by comparing the internal consistency credibility coefficient with the credibility threshold;

[0104] Determine the resident health monitoring verification result, and when the internal consistency credibility coefficient is greater than or equal to the credibility threshold, feedback the resident health monitoring data credibility result;

[0105] When the internal consistency credibility coefficient is less than the credibility threshold, the deviation result of the resident health monitoring data is fed back to the intelligent health monitoring database and the deviation data is eliminated.

[0106] In this embodiment, a resident health monitoring coefficient is obtained through the resident health monitoring data, and the resident health monitoring coefficient includes a resident information data risk coefficient and a resident health data risk coefficient. A resident health monitoring model is constructed through the resident health monitoring coefficient and the resident health level is obtained. The resident health level includes a health level, a sub-health level, a disease precursor level, and a disease level. This can be specifically achieved by the following steps:

[0107] S301: Obtain a resident information data coefficient through the resident information data, the resident information data coefficient includes a resident family medical history information coefficient, a resident gender information coefficient, a resident age information coefficient, and a resident weight information coefficient, and calculate the resident information data risk coefficient according to the resident information data coefficient. The calculation formula of the resident information data risk coefficient is:

[0108]

[0109] Among them, θ is the risk coefficient of resident information data, v is the information coefficient of resident family medical history, which is 1.4 when both parents of the resident die of disease, 1.2 when one of the parents of the resident dies of disease, 1 when the parents of the resident are alive, and 0.8 when the parents of the resident are alive and both are over 60 years old, U is the information coefficient of resident gender, which is 0.6 when the resident is female, and 0.8 when the resident is male, O is the information coefficient of resident age, which is 1 when the resident is under 35 years old, 1.4 when the resident is between 35 and 59 years old, and 1.8 when the resident is over 59 years old, L is the information coefficient of resident weight, which is 2.5 when the resident weight fluctuates by more than 75% of the standard weight, 1.5 when the resident weight fluctuates by 50% to 75% of the standard weight, and 1 when the resident weight fluctuates by less than 50% of the standard weight, and D is the annual average mortality rate of the resident's location, in %.

[0110] S302: Obtain the resident health coefficient through the resident health data, the resident health coefficient includes the resident basic health coefficient, the resident deep health coefficient, and the resident self-assessed health coefficient. The resident health coefficient is determined according to the actual test items. The resident health data risk coefficient is calculated according to the resident health coefficient. The calculation formula of the resident health data risk coefficient is:

[0111] η=η1+η2+η3,

[0112] Among them, η is the risk coefficient of residents' health data, η1 is the basic health coefficient of residents, η2 is the deep health coefficient of residents, and η3 is the self-assessed health coefficient of residents;

[0113] S303: Calculate the resident health level evaluation index through the resident health monitoring coefficient and construct a resident health monitoring model. The calculation formula of the resident health level evaluation index is:

[0114]

[0115] Among them, ψ is the resident health level evaluation index, θ is the resident information data risk coefficient, and η is the resident health data risk coefficient;

[0116] S304: Preset a resident health level evaluation threshold, which includes a resident health level threshold, a resident sub-health level threshold, a resident disease precursor level threshold, and a resident disease level threshold, and obtain the resident health level by comparing the resident health level evaluation threshold with the resident health level evaluation index;

[0117] Determine the resident health level evaluation index, and when the resident health level evaluation index is less than or equal to the resident health level threshold, feedback the health level;

[0118] When the resident health level evaluation index is less than or equal to the resident sub-health level threshold and greater than the resident health level threshold, the sub-health level is fed back;

[0119] When the resident health level evaluation index is less than or equal to the resident disease precursor level threshold and greater than the resident sub-health level threshold, the disease precursor level is fed back;

[0120] When the resident health level evaluation index is less than or equal to the resident disease level threshold and greater than the resident disease precursor level threshold, the disease level is fed back;

[0121] In this embodiment, follow-up information is obtained based on the resident's health level, and the resident is followed up until the resident dies through the follow-up information, so as to reduce the possibility of delay in the resident's illness due to various factors without physical examination, and obtain follow-up health monitoring data, which can be implemented specifically through the following steps:

[0122] The follow-up information includes long-term follow-up information, medium-long-term follow-up information, medium-short-term follow-up information, and short-term follow-up information. Residents of the health level are followed up according to the long-term follow-up information, residents of the sub-health level are followed up according to the medium-long-term follow-up information, residents of the disease precursor level are followed up according to the medium-short-term follow-up information, and residents of the disease level are followed up according to the short-time span follow-up information, thereby saving manpower and material resources in the follow-up process. The measure of shortening the follow-up time span for the sick population can timely discover the onset of the disease in the sick population and take rescue measures in time. The follow-up health monitoring data includes but is not limited to routine blood data, routine urine data, liver function data, kidney function data, and blood pressure data.

[0123] In this embodiment, the follow-up health monitoring data is screened by data screening and the follow-up screening results are obtained, and the follow-up screening results include low disease risk results and high disease risk results, which can be specifically implemented by the following steps:

[0124] Preset a high-risk health threshold, which includes but is not limited to a high-risk threshold for routine blood data, a high-risk threshold for routine urine data, a high-risk threshold for liver function data, a high-risk threshold for renal function data, and a high-risk threshold for blood pressure data, and obtain the follow-up screening result by comparing the follow-up health monitoring data with the high-risk health threshold;

[0125] Determine the follow-up health monitoring data, and when two or more of the follow-up health monitoring data are greater than the high-risk health threshold, feedback the low-risk result;

[0126] When two or more of the follow-up health monitoring data are greater than the high-risk health threshold, the high risk result is fed back to the resident terminal, and a health warning message is sent to the resident to prevent the possibility of the resident getting sick in advance.

[0127] A resident health monitoring device based on follow-up, comprising a data acquisition module, a data verification module, a health grade evaluation module, a resident follow-up module, and a follow-up screening module;

[0128] The data acquisition module is used to collect resident health monitoring data and upload it to the intelligent health monitoring database. The resident health monitoring data includes resident information data and resident health data. The resident health data includes resident basic health data, resident in-depth health data, and resident electronic self-assessment health data;

[0129] The data verification module is used to verify the resident health monitoring data through credibility analysis and obtain resident health monitoring verification results, wherein the resident health monitoring verification results include resident health monitoring data credibility results and resident health monitoring data deviation results;

[0130] The health grade evaluation module is used to obtain the resident health monitoring coefficient through the resident health monitoring data, and the resident health monitoring coefficient includes the resident information data risk coefficient and the resident health data risk coefficient. The resident health monitoring model is constructed through the resident health monitoring coefficient and the resident health grade is obtained. The resident health grade includes the health grade, sub-health grade, disease precursor grade, and disease grade;

[0131] The resident follow-up module is used to obtain follow-up information based on the resident health level, follow up the resident until the resident dies through the follow-up information, and obtain follow-up health monitoring data;

[0132] The follow-up screening module is used to screen the follow-up health monitoring data through data screening and obtain follow-up screening results, and the follow-up screening results include low disease risk results and high disease risk results.

[0133] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0134] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0135] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0136] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A resident health monitoring method based on follow-up, characterized in that: The implementation of the resident health monitoring method comprises the following steps: S1: Collecting resident health monitoring data and uploading it to the intelligent health monitoring database, wherein the resident health monitoring data includes resident information data and resident health data, wherein the resident health data includes resident basic health data, resident in-depth health data, and resident electronic self-assessment health data; S2: verifying the resident health monitoring data through credibility analysis and obtaining resident health monitoring verification results, wherein the resident health monitoring verification results include resident health monitoring data credibility results and resident health monitoring data deviation results; S3: Obtain a resident health monitoring coefficient through the resident health monitoring data, the resident health monitoring coefficient includes a resident information data risk coefficient and a resident health data risk coefficient, and construct a resident health monitoring model through the resident health monitoring coefficient and obtain the resident health level, the resident health level includes a health level, a sub-health level, a disease precursor level, and a disease level; S4: Obtaining follow-up information based on the resident's health level, following up the resident until the resident dies through the follow-up information, and obtaining follow-up health monitoring data; S5: Screening the follow-up health monitoring data through data screening and obtaining follow-up screening results, wherein the follow-up screening results include low disease risk results and high disease risk results.

2. The resident health monitoring method according to claim 1, characterized in that: The step S1 specifically includes: S101: Obtaining basic health data of the resident through a smart monitoring bracelet, where the basic health data of the resident includes heart rate, respiratory rate, blood oxygen saturation, pressure value, and temperature; S102: Acquire the in-depth health data of the resident through health examination, wherein the in-depth health data of the resident includes internal medicine data, surgical data, ENT data, oncology data, and infectious disease data; S103: Obtain the residents' self-assessment health questionnaire through a questionnaire survey and extract the residents' electronic self-assessment health data, the questionnaire survey includes an electronic questionnaire survey and a paper questionnaire survey, the residents' self-assessment health questionnaire includes a normal residents' electronic self-assessment health questionnaire and a special residents' paper self-assessment health questionnaire, the residents' electronic self-assessment health data includes normal residents' electronic self-assessment health data and special residents' electronic self-assessment health data, obtain the normal residents' electronic self-assessment health data through the normal residents' electronic self-assessment health questionnaire, process the special residents' paper self-assessment health questionnaire through an improved questionnaire recognition method and obtain the special residents' electronic self-assessment health data.

3. The resident health monitoring method according to claim 2, characterized in that: The step S103 specifically includes: S103-1: photographing the paper self-assessment health questionnaire for special residents by means of a photographing device and obtaining a set of images of the paper self-assessment health questionnaire for special residents; S103-2: performing normalization processing on the special resident paper self-assessment health questionnaire image set and obtaining a normalized special resident paper self-assessment health questionnaire image set, wherein the normalization processing is to make the size of each special resident paper self-assessment health questionnaire image in the special resident paper self-assessment health questionnaire image set consistent by image cutting; S103-3: Based on the weighted average method, the normalized special resident paper self-assessment health questionnaire image set is processed by grayscale and a grayscale special resident paper self-assessment health questionnaire image set is obtained, wherein the grayscale is to convert the color image into a gray image, and the expression of the weighted average method is: Gray=0.299R+0.587G+0.114B, Among them, Gray is the gray value, R is the brightness of the red channel, G is the brightness of the green channel, and B is the brightness of the blue channel; S103-4: Obtain the longest line segment inclination angle of a single image in the grayscale special resident paper self-assessment health questionnaire image set, calculate the inclination angle of the single image according to the longest line segment inclination angle, rotate the single image according to the inclination angle and obtain the modified special resident paper self-assessment health questionnaire image set, the calculation formula of the inclination angle is: Among them, β is the tilt angle, α is the tilt angle of the longest line segment; S103-5: Identify the modified special resident paper self-assessment health questionnaire image set through character recognition and obtain the special resident electronic self-assessment health data.

4. The resident health monitoring method according to claim 1, characterized in that: The step S2 specifically includes: S201: Obtaining the internal consistency credibility coefficient of the resident health monitoring data, the calculation formula of the internal consistency credibility coefficient is: Among them, γ is the internal consistency reliability coefficient, k is the total number of residents’ health monitoring data, S is the variance of residents’ health monitoring data, S i is the variance of the health monitoring data of the ith resident; S202: Preset a credibility threshold, and obtain the resident health monitoring verification result by comparing the internal consistency credibility coefficient with the credibility threshold; Determine the resident health monitoring verification result, and when the internal consistency credibility coefficient is greater than or equal to the credibility threshold, feedback the resident health monitoring data credibility result; When the internal consistency credibility coefficient is less than the credibility threshold, the deviation result of the resident health monitoring data is fed back to the intelligent health monitoring database and the deviation data is eliminated.

5. The resident health monitoring method according to claim 1, characterized in that: The step S3 specifically includes: S301: Obtain a resident information data coefficient through the resident information data, the resident information data coefficient includes a resident family medical history information coefficient, a resident gender information coefficient, a resident age information coefficient, and a resident weight information coefficient, and calculate the resident information data risk coefficient according to the resident information data coefficient. The calculation formula of the resident information data risk coefficient is: Among them, θ is the risk coefficient of resident information data, v is the coefficient of resident family history information, U is the coefficient of resident gender information, O is the coefficient of resident age information, L is the coefficient of resident weight information, and D is the average annual mortality rate of the resident’s location; S302: Obtain the resident health coefficient through the resident health data, the resident health coefficient includes the resident basic health coefficient, the resident deep health coefficient, and the resident self-assessed health coefficient, and calculate the resident health data risk coefficient according to the resident health coefficient. The calculation formula of the resident health data risk coefficient is: η=η1+η2+η3, Among them, η is the risk coefficient of residents' health data, η1 is the basic health coefficient of residents, η2 is the deep health coefficient of residents, and η3 is the self-assessed health coefficient of residents; S303: Calculate the resident health level evaluation index through the resident health monitoring coefficient and construct a resident health monitoring model. The calculation formula of the resident health level evaluation index is: Among them, ψ is the resident health level evaluation index, θ is the resident information data risk coefficient, and η is the resident health data risk coefficient; S304: Preset a resident health level evaluation threshold, which includes a resident health level threshold, a resident sub-health level threshold, a resident disease precursor level threshold, and a resident disease level threshold, and obtain the resident health level by comparing the resident health level evaluation threshold with the resident health level evaluation index; Determine the resident health level evaluation index, and when the resident health level evaluation index is less than or equal to the resident health level threshold, feedback the health level; When the resident health level evaluation index is less than or equal to the resident sub-health level threshold and greater than the resident health level threshold, the sub-health level is fed back; When the resident health level evaluation index is less than or equal to the resident disease precursor level threshold and greater than the resident sub-health level threshold, the disease precursor level is fed back; When the resident health level evaluation index is less than or equal to the resident disease level threshold and greater than the resident disease precursor level threshold, the disease level is fed back.

6. The resident health monitoring method according to claim 1, characterized in that: The step S4 is specifically as follows: The follow-up information includes long-term follow-up information, medium-to-long-term follow-up information, medium-to-short-term follow-up information, and short-term follow-up information. Residents of the health level are followed up according to the long-term follow-up information, residents of the sub-health level are followed up according to the medium-to-long-term follow-up information, residents of the disease precursor level are followed up according to the medium-to-short-term follow-up information, and residents of the disease level are followed up according to the short-time span follow-up information. The follow-up health monitoring data includes routine blood data, routine urine data, liver function data, kidney function data, and blood pressure data.

7. The resident health monitoring method according to claim 1, characterized in that: The step S5 is specifically as follows: Preset high-risk health thresholds, which include high-risk thresholds for routine blood data, high-risk thresholds for routine urine data, high-risk thresholds for liver function data, high-risk thresholds for renal function data, and high-risk thresholds for blood pressure data, and obtain the follow-up screening results by comparing the follow-up health monitoring data with the high-risk health thresholds; Determine the follow-up health monitoring data, and when two or more of the follow-up health monitoring data are greater than the high-risk health threshold, feedback the low-risk result; When two or more of the follow-up health monitoring data are greater than the high-risk health threshold, the high risk result is fed back to the resident terminal and a health warning message is sent to the resident.

8. A resident health monitoring device based on follow-up, characterized in that: It includes data acquisition module, data verification module, health grade evaluation module, resident follow-up module and follow-up screening module; The data acquisition module is used to collect resident health monitoring data and upload it to the intelligent health monitoring database. The resident health monitoring data includes resident information data and resident health data. The resident health data includes resident basic health data, resident in-depth health data, and resident electronic self-assessment health data; The data verification module is used to verify the resident health monitoring data through credibility analysis and obtain resident health monitoring verification results, wherein the resident health monitoring verification results include resident health monitoring data credibility results and resident health monitoring data deviation results; The health grade evaluation module is used to obtain the resident health monitoring coefficient through the resident health monitoring data, and the resident health monitoring coefficient includes the resident information data risk coefficient and the resident health data risk coefficient. The resident health monitoring model is constructed through the resident health monitoring coefficient and the resident health grade is obtained. The resident health grade includes the health grade, sub-health grade, disease precursor grade, and disease grade; The resident follow-up module is used to obtain follow-up information based on the resident health level, follow up the resident until the resident dies through the follow-up information, and obtain follow-up health monitoring data; The follow-up screening module is used to screen the follow-up health monitoring data through data screening and obtain follow-up screening results, and the follow-up screening results include low disease risk results and high disease risk results.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the resident health monitoring method as described in any one of claims 1-7 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the resident health monitoring method as described in any one of claims 1-7.